{"id":"W4362676437","doi":"10.1145/3586049","title":"Pushing the Limit of 1-Minimality of Language-Agnostic Program Reduction","year":2023,"lang":"en","type":"article","venue":"Proceedings of the ACM on Programming Languages","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Debugging; Programming language; Reduction (mathematics); Computer science; Syntax; Implementation; Theoretical computer science; Artificial intelligence; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008714531,0.001634983,0.001275077,0.001829785,0.001442367,0.003459376,0.004840057,0.001669426,0.003229804],"category_scores_gemma":[0.03045063,0.00152441,0.002411319,0.001040406,0.006512125,0.008768667,0.00775985,0.005549036,0.001119099],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001952737,"about_ca_system_score_gemma":0.00405006,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001405933,"about_ca_topic_score_gemma":0.002611323,"domain_scores_codex":[0.9875048,0.003637926,0.0008495531,0.002317393,0.004726996,0.0009633507],"domain_scores_gemma":[0.9657926,0.0178357,0.002181229,0.01092895,0.002818373,0.000443046],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0005299249,0.0004147398,0.004441574,0.00209866,0.0002198784,0.0005417875,0.001690357,0.06674919,0.06369172,0.5121967,0.00911694,0.3383086],"study_design_scores_gemma":[0.0001580676,0.0006112027,0.001015372,0.0005570378,0.0002815256,0.0009823708,0.0003497612,0.2292443,0.07417994,0.6370975,0.05534343,0.0001794427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0329999,0.00122798,0.9450559,0.002413285,0.0001368366,0.0001962357,0.0001329528,0.007952049,0.009884835],"genre_scores_gemma":[0.2648432,0.000905393,0.7241374,0.001463065,0.0001562598,0.0004004718,0.0003347942,0.003849895,0.00390956],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.008714531,"threshold_uncertainty_score":0.04608738,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02725027826828869,"score_gpt":0.3119918759498543,"score_spread":0.2847415976815656,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}